Hierarchical Feature Fusion Triple Network for Change Detection With Bitemporal Remote Sensing Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 63; pp. 1 - 12
• Main Authors: Lv, Zhiyong, Yang, Tianyv, Zhong, Pingdong, Sun, Weiwei, Atli Benediktsson, Jon, Li, Junhuai
• Format: Journal Article
• Language: English
• Published: New York IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Change detection; Convolution; Convolutional neural networks; Earth surface; False alarms; Feature extraction; Imaging; Kernel; Land cover; Land cover change detection (LCCD); Learning; Modules; neural network; Neural networks; Noise; Noise reduction; Performance enhancement; Reflectance; Remote sensing; remotely sensed images (RSIs); Shape; Transformers
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2025.3525811

Achieving land cover change detection (LCCD) through remotely sensed images (RSIs) is important in the observation of the changes on the Earth's surface. In such detection, spectral-reflectance noise and the uncertainty of the imaging external conditions for the bitemporal RSIs usually cause some salt-and-pepper noisy pixels in the results and reduce the change detection accuracy. In this article, a hierarchical feature-fusion triple network (HFTN) is proposed to improve the performance of LCCD with RSIs. Overall, the proposed HFTN aims to learn representative features to improve change detection performance via two feature learning enhancement strategies and a hierarchical feature-fusion mechanism. First, an image feature difference model is proposed to generate the input feature for the middle branch and guide the learning performance. Second, a progressive denoising module (PDM) is proposed and applied to each temporal image to reduce the noise before feeding the features into the backbone of the proposed HFTN. Finally, a hierarchical feature-fusion module (HFFM) is proposed to fuse the learned deep feature for generating a change-magnitude image. Additionally, multiscale convolution, cross-scale fusion, and a shared weight are adopted in the backbone of the proposed HFTN to further enhance the feature learning performance. Compared with eight state-of-the-art methods, experimental results verified the feasibility and superiority of the proposed HFTN for LCCD with RSIs. For example, the proposed HFTN achieved improvement rates of approximately 0.43%-11.83% for overall accuracy (OA) and 0.11%-4.81% for false alarms (FAs) across six pairs of real RSIs. The code can be available at https://github.com/ImgSciGroup/HFTN-NET.git .